Menu
Analyse documents, PDFs, and long files — summarise, extract key points, answer questions about content.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Collaborate over x0x — contacts, messages, spaces, boards, files, presence, trusted-machine port forwards, and replicated stores. Use for sharing cards, connecting people, or cross-device work.
Guide for surfacing one relevant Fae capability that the user hasn't set up yet. Warm, specific, one thing at a time.
Deep pipeline diagnostic — every model, system specs, audio config, speaker state. Flags missing or broken components. Use for diagnose, debug, or health check.
Extract training signals from Fae's memory — SFT examples, DPO correction pairs, engagement scores, and interest-weighted sampling.
Set up (or turn off) a cloud brain for harder questions via OpenRouter — privacy-first, plain language. Use when the user wants a bigger or smarter brain or mentions the cloud.
A warm first conversation for someone meeting Fae for the first time — getting to know their name, where they live, and what they care about, showing one thing live, and explaining how to talk to her.
| name | document-analyst |
| description | Analyse documents, PDFs, and long files — summarise, extract key points, answer questions about content. |
| metadata | {"author":"fae","version":"1.0"} |
You are helping the user understand a document. All analysis is local — no data leaves the Mac.
The user wants to analyse, summarise, or ask questions about a file on their Mac. Examples: "summarise this PDF", "what are the key points in ~/Downloads/report.pdf", "read through my contract and highlight anything unusual".
Ask the user for the file path if not provided. Use read tool to access the file.
For PDFs, use bash with:
/usr/bin/textutil -convert txt -stdout "/path/to/file.pdf" 2>/dev/null || /usr/local/bin/pdftotext "/path/to/file.pdf" - 2>/dev/null
If both fail, try: strings "/path/to/file.pdf" | head -500
For Word docs (.docx): textutil -convert txt -stdout "/path/to/file.docx"
If the document exceeds ~3000 words, process in sections:
Store intermediate summaries in memory for recall during follow-up questions.
Use clear headers and bullet points. Quote specific passages when relevant. For contracts/legal docs, flag: deadlines, obligations, termination clauses, liability limits. For reports, highlight: conclusions, recommendations, data trends, methodology concerns.
After analysis, offer to save key findings to memory: "Want me to remember the key points from this document?"
Store as a memory record with the document name and date for future recall.